Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 793 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2605. Min Act: -0.0002

Data Index: 1163041 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2176. Min Act: -0.0002

Data Index: 866395 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2167. Min Act: -0.0002

Data Index: 71231 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2078. Min Act: -0.0002

Data Index: 403297 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2045. Min Act: -0.0002

Data Index: 940433 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.2034. Min Act: -0.0002

Data Index: 320040 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1888. Min Act: -0.0002

Data Index: 984257 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1822. Min Act: -0.0002

Data Index: 1235477 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1895. Min Act: -0.0002

Data Index: 67161 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1833. Min Act: -0.0002

Data Index: 373780 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1813. Min Act: -0.0002

Data Index: 8789 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1676. Min Act: -0.0002

Data Index: 177302 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1719. Min Act: -0.0002

Data Index: 266709 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1678. Min Act: -0.0002

Data Index: 1332026 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1682. Min Act: -0.0002

Data Index: 543123 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1672. Min Act: -0.0002

Data Index: 868880 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1671. Min Act: -0.0002

Data Index: 1081961 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1606. Min Act: -0.0002

Data Index: 921288 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1709. Min Act: -0.0002

Data Index: 595564 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.2605. Min Range: -0.2605

Max Act: 0.1642. Min Act: -0.0002

Data Index: 614140 (C4 (Web Text))

Max Activating Token Index: 854